Comparative performances of machine learning algorithms in radiomics and impacting factors (preprint)

There are no current recommendations on which machine learning (ML) algorithms should be used in radiomics. The objective was to compare performances of ML algorithms in radiomics when applied to different clinical questions to determine whether some strategies could give the best and most stable performances regardless of datasets. This study compares the performances of nine feature selection algorithms combined with fourteen binary classification algorithms on ten datasets. These datasets included radiomics features and clinical diagnosis for binary clinical classifications including COVID-19 pneumonia or sarcopenia on CT, head and neck, orbital or uterine lesions on MRI. For each dataset, a train-test split was created. Each of the 126 (9 x 14) combinations of feature selection algorithms and classification algorithms was trained and tuned using a ten-fold cross validation, then AUC was computed. This procedure was repeated three times per dataset. Best overall performances were obtained with JMI and JMIM as feature selection algorithms and random forest and linear regression models as classification algorithms. The choice of the classification algorithm was the factor explaining most of the performance variation (10% of total variance). The choice of the feature selection algorithm explained only 2% of variation, while the train-test split explained 9%.

AI-Driven CT-based quantification, staging and short-term outcome prediction of COVID-19 pneumonia (preprint)

Improving screening, discovering therapies, developing a vaccine and performing staging and prognosis are decisive steps in addressing the COVID-19 pandemic. Staging and prognosis are especially crucial for organizational anticipation (intensive-care bed availability, patient management planning) and accelerating drug development; through rapid, reproducible and quantified response-to-treatment assessment. In this letter, we report on an artificial intelligence solution for performing automatic staging and prognosis based on imaging, clinical, comorbidities and biological data. This approach relies on automatic computed tomography (CT)-based disease quantification using deep learning, robust data-driven identification of physiologically-inspired COVID-19 holistic patient profiling, and strong, reproducible staging/outcome prediction with good generalization properties using an ensemble of consensus methods. Highly promising results on multiple independent external evaluation cohorts along with comparisons with expert human readers demonstrate the potentials of our approach. The developed solution offers perspectives for optimal patient management, given the shortage of intensive care beds and ventilators1, 2, along with means to assess patient response to treatment.

AI-Driven CT-based quantification, staging and short-term outcome prediction of COVID-19 pneumonia (preprint)

Chest computed tomography (CT) is widely used for the management of Coronavirus disease 2019 (COVID-19) pneumonia because of its availability and rapidity. The standard of reference for confirming COVID-19 relies on microbiological tests but these tests might not be available in an emergency setting and their results are not immediately available, contrary to CT. In addition to its role for early diagnosis, CT has a prognostic role by allowing visually evaluating the extent of COVID-19 lung abnormalities. The objective of this study is to address prediction of short-term outcomes, especially need for mechanical ventilation. In this multi-centric study, we propose an end-to-end artificial intelligence solution for automatic quantification and prognosis assessment by combining automatic CT delineation of lung disease meeting performance of experts and data-driven identification of biomarkers for its prognosis. AI-driven combination of variables with CT-based biomarkers offers perspectives for optimal patient management given the shortage of intensive care beds and ventilators.